TranslatedUI design skill for Claude Code, Codex and other AI agents: explore distinct directions, compare them side by side, refine against real screenshots. A UI design Skill for AI Agents.
- agent-skills
- ai-design
- claude-code
- claude-skills
71,372 visible repositories in the index
25–48 of 94 · Most stars
TranslatedUI design skill for Claude Code, Codex and other AI agents: explore distinct directions, compare them side by side, refine against real screenshots. A UI design Skill for AI Agents.
QualityScaler - image/video AI upscaler app
Codex Autoresearch Skill — A self-directed iterative system for Codex that continuously cycles through: modify, verify, retain or discard, and repeat indefinitely. Inspired by Karpathy’s autoresearch concept.
All In One Web Recon
A bidirectional pipeline parallelism algorithm for computation-communication overlap in DeepSeek V3/R1 training.
Reference implementation for DPO (Direct Preference Optimization)
Turn one topic into a finished Vox-style paper-collage explainer/ad video — automated end to end on Atlas Cloud + ffmpeg. An agent skill.
Concatenate a directory full of files into a single prompt for use with LLMs
A collection of Azure AD/Entra tools for offensive and defensive security purposes
Run the full 2.78-trillion-parameter Kimi K3 model, DeepSeek V4.1 Flash or GLM-5.3-Flash beyond available RAM by streaming activated weights directly from NVMe. A dependency-free, embeddable C inference engine.
ACM-ICPC Preparation Guide
A Python based ingestor for BloodHound
Stable Diffusion web UI
BloodyAD is an Active Directory Privilege Escalation Framework
FakeNet-NG - Next Generation Dynamic Network Analysis Tool
HTTP/HTTP2/HTTP3/Socks4/Socks5/Shadowsocks/ShadowsocksR/SSH/Redirect/Pf TCP/UDP asynchronous tunnel proxy implemented in Python 3 asyncio.
Translate GPU shaders and compute kernels between GLSL, HLSL, Metal, SPIR-V, Slang, CUDA and HIP, and to WGSL, through the CrossGL IR
A security tool for multithreaded information gathering and service enumeration whilst building directory structures to store results, along with writing out recommendations for further testing.
This may be the simplest implement of DDPM. You can directly run Main.py to train the UNet on CIFAR-10 dataset and see the amazing process of denoising.
Plugin to generate BOM + CPL files for JLCPCB, assigning LCSC part numbers directly from the plugin, query the JLCPCB parts database, lookup datasheets and much more.
TranslatedManju Laoli (漫剧老李, "Comic Drama Old Li") AIGC full-workflow creation Skill · V7.4.26 multi-skill suite edition (Short-Drama Director Suite): 1 master controller + 12 sub-skills · four-layer deep architecture — genre routing / material scouting / script / assets / storyboard / three major fight-scene engines / feeding / quality inspection across the whole chain. Six pre-locks + I art-style lock · 50 rule libraries · machine checks C1~C33 | H1~H12 + six feeding gates + P4.5 storyboard machine checks (P450~P458) · material forms M0/M1/M2 (this package does not hold images) · outputs seven-section prompt sets that can be fed directly into Seedance 2.5 / 2.0 / MiniMax H3. Beta version, a secondary modification that integrates open-source content.
Find web directories without bruteforce
pwning IPv4 via IPv6
Computer Vision library for human-computer interaction. It implements Head Pose and Gaze Direction Estimation Using Convolutional Neural Networks, Skin Detection through Backprojection, Motion Detection and Tracking, Saliency Map.